CVE-2026-33235: CWE-400: Uncontrolled Resource Consumption in Significant-Gravitas AutoGPT
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service (DoS) attack. While the backend implements a SandboxedEnvironment to prevent unauthorized attribute access (e.g., blocking __class__), it fails to limit the computational complexity or execution time of the expressions. An attacker can input computationally expensive Python/Jinja2 expressions that consume the server's CPU and memory, leading to a complete system hang or crash. In multi-tenant or self-hosted environments, this results in a complete service outage and "noisy neighbor" effects that require manual administrative intervention to recover. This issue has been fixed in version 0.6.52.
AI Analysis
Technical Summary
CVE-2026-33235 describes an uncontrolled resource consumption vulnerability (CWE-400) in Significant-Gravitas AutoGPT before version 0.6.52. The Fill Text Template block allows attackers to submit computationally expensive Python/Jinja2 expressions that exhaust server CPU and memory resources. Although the backend sandbox prevents unauthorized attribute access, it does not restrict the complexity or execution time of expressions, enabling denial of service conditions. This can cause complete service outages and noisy neighbor effects in multi-tenant or self-hosted environments. The vulnerability is resolved in version 0.6.52.
Potential Impact
Successful exploitation leads to denial of service by exhausting CPU and memory resources, causing system hangs or crashes. This results in complete service outages and noisy neighbor effects in environments hosting multiple tenants or self-hosted instances. There is no impact on confidentiality or integrity, but availability is severely affected.
Mitigation Recommendations
Upgrade AutoGPT to version 0.6.52 or later, where this vulnerability is fixed. No other official remediation or temporary fixes are indicated. Manual administrative intervention is required to recover from exploitation in affected versions.
CVE-2026-33235: CWE-400: Uncontrolled Resource Consumption in Significant-Gravitas AutoGPT
Description
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service (DoS) attack. While the backend implements a SandboxedEnvironment to prevent unauthorized attribute access (e.g., blocking __class__), it fails to limit the computational complexity or execution time of the expressions. An attacker can input computationally expensive Python/Jinja2 expressions that consume the server's CPU and memory, leading to a complete system hang or crash. In multi-tenant or self-hosted environments, this results in a complete service outage and "noisy neighbor" effects that require manual administrative intervention to recover. This issue has been fixed in version 0.6.52.
CVSS v3.1
Score 7.7high
Affected software
pkg:github/significant-gravitas/AutoGPTRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-33235 describes an uncontrolled resource consumption vulnerability (CWE-400) in Significant-Gravitas AutoGPT before version 0.6.52. The Fill Text Template block allows attackers to submit computationally expensive Python/Jinja2 expressions that exhaust server CPU and memory resources. Although the backend sandbox prevents unauthorized attribute access, it does not restrict the complexity or execution time of expressions, enabling denial of service conditions. This can cause complete service outages and noisy neighbor effects in multi-tenant or self-hosted environments. The vulnerability is resolved in version 0.6.52.
Potential Impact
Successful exploitation leads to denial of service by exhausting CPU and memory resources, causing system hangs or crashes. This results in complete service outages and noisy neighbor effects in environments hosting multiple tenants or self-hosted instances. There is no impact on confidentiality or integrity, but availability is severely affected.
Mitigation Recommendations
Upgrade AutoGPT to version 0.6.52 or later, where this vulnerability is fixed. No other official remediation or temporary fixes are indicated. Manual administrative intervention is required to recover from exploitation in affected versions.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-03-18T02:42:27.508Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a3c4ce14853345fc1df8ce5
Added to database: 06/24/2026, 21:32:17 UTC
Last enriched: 07/01/2026, 22:38:50 UTC
Last updated: 08/09/2026, 00:41:13 UTC
Views: 74
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.